当前位置: X-MOL 学术Quantum Sci. Technol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A quantum deep convolutional neural network for image recognition
Quantum Science and Technology ( IF 5.6 ) Pub Date : 2020-07-19 , DOI: 10.1088/2058-9565/ab9f93
YaoChong Li 1, 2 , Ri-Gui Zhou 1, 2 , RuQing Xu 1, 2 , Jia Luo 1, 2 , WenWen Hu 1, 2
Affiliation  

Deep learning achieves unprecedented success involves many fields, whereas the high requirement of memory and time efficiency tolerance have been the intractable challenges for a long time. On the other hand, quantum computing shows its superiorities in some computation problems owing to its intrinsic properties of superposition and entanglement, which may provide a new path to settle these issues. In this paper, a quantum deep convolutional neural network (QDCNN) model based on the quantum parameterized circuit for image recognition is investigated. In analogy to the classical deep convolutional neural network (DCNN), the architecture that a sequence of quantum convolutional layers followed by a quantum classified layer is illustrated. Inspired by the variational quantum algorithms, a quantum–classical hybrid training scheme is demonstrated for the parameter updating in the QDCNN. The network complexity analysis indicates the proposed model provides the exponential acceleration...

中文翻译:

量子深度卷积神经网络的图像识别

深度学习取得了空前的成功,涉及许多领域,而对内存的高要求和对时间效率的耐受性一直是棘手的挑战。另一方面,由于量子计算的叠加和纠缠的内在特性,在某些计算问题上显示了其优越性,这可能为解决这些问题提供新的途径。本文研究了一种基于量子参数化电路的量子深度卷积神经网络模型。类似于经典的深度卷积神经网络(DCNN),说明了一系列的量子卷积层,然后是量子分类层的体系结构。受变分量子算法的启发,量子经典混合训练方案被证明用于QDCNN中的参数更新。网络复杂度分析表明,所提出的模型提供了指数加速。
更新日期:2020-07-20
down
wechat
bug